Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2658 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.3171. Min Act: -0.0000

Data Index: 630405 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2367. Min Act: -0.0001

Data Index: 856416 (C4 (Web Text))

Max Activating Token Index: 774

Text #2

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2390. Min Act: -0.0000

Data Index: 1104607 (C4 (Web Text))

Max Activating Token Index: 823

Text #3

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2407. Min Act: -0.0001

Data Index: 289165 (C4 (Web Text))

Max Activating Token Index: 913

Text #4

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2112. Min Act: -0.0001

Data Index: 297527 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2361. Min Act: -0.0001

Data Index: 53902 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2117. Min Act: -0.0001

Data Index: 1328759 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2385. Min Act: -0.0000

Data Index: 861578 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2020. Min Act: -0.0000

Data Index: 433478 (C4 (Web Text))

Max Activating Token Index: 548

Text #9

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1033371 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2077. Min Act: -0.0001

Data Index: 688006 (C4 (Web Text))

Max Activating Token Index: 910

Text #11

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2017. Min Act: -0.0000

Data Index: 375010 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2003. Min Act: -0.0001

Data Index: 801551 (C4 (Web Text))

Max Activating Token Index: 668

Text #13

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2029. Min Act: -0.0001

Data Index: 65362 (C4 (Web Text))

Max Activating Token Index: 986

Text #14

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1881. Min Act: -0.0000

Data Index: 944055 (C4 (Web Text))

Max Activating Token Index: 961

Text #15

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1997. Min Act: -0.0001

Data Index: 97511 (C4 (Web Text))

Max Activating Token Index: 654

Text #16

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2052. Min Act: -0.0001

Data Index: 790840 (C4 (Web Text))

Max Activating Token Index: 423

Text #17

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2048. Min Act: -0.0001

Data Index: 261537 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.2015. Min Act: -0.0000

Data Index: 140727 (C4 (Web Text))

Max Activating Token Index: 594

Text #19

Max Range: 0.3171. Min Range: -0.3171

Max Act: 0.1915. Min Act: -0.0000

Data Index: 228288 (C4 (Web Text))

Max Activating Token Index: 454